Detection of grinding surface damage of nanocrystalline optical glass based on wavelet transfinite learning machine

Abstract

The traditional grinding surface damage detection of nanocrystalline optical glass materials has the problems of low detection accuracy and large calculation error of damage point displacement. A grinding surface damage detection method of nanocrystalline optical glass based on wavelet transfinite learning machine is proposed. Nanocrystalline optical glass materials were prepared by melt quenching method; The surface grinding is completed by diamond grinding wheel, the included angle of grinding direction is determined, and the light scattering intensity of material surface damage is determined by light scattering intensity; The wavelet basis is selected by wavelet smoothing function to determine the location and amount of surface damage; The displacement array of damage points is obtained by transfinite learning machine, and the surface damage detection model is constructed to realise damage detection. The results show that the proposed method improves the damage detection accuracy and reduces the calculation error of damage point displacement.